An AI Tutor That Knows Which Course You Are In

The server builds a packet of your real course material and instructs the model to answer from it. Here is what goes in.

Your class meetings, labs and discussion sections included, since those are stored as their own meeting kinds. Your grading scale, as plain text — A at 93 percent and up, B at 83 and up, or whatever your school actually uses, if you have customized it.

The structured items from your most recent syllabus scan: capped at 8,000 characters and up to 60 items. And your currently tracked deadlines: also capped at 8,000 characters and up to 60 tasks.

The grade figures shown on that course's screen, covered below. And your uploaded notes, picked by how well they match your question: it looks through up to 24 of the course's most recent files and reads the best matches first, up to 24,000 characters in all and no more than 8,000 from any one file. If nothing in the question points to a particular file, the newest come first. A syllabus or deadlines block that has to be cut is clearly marked as shortened, so the model knows it is working from part of the list rather than treating it as complete.

• Class meetings, including labs and discussion sections
• Your grading scale, customized cutoffs included
• Syllabus: 8,000 characters, up to 60 items
• Deadlines: 8,000 characters, up to 60 tasks
• The grades on your course screen
• Notes: best matches from your 24 most recent files, 24,000 characters shared

This is the constraint that matters most, because it is the one where a confident wrong answer does real damage.

For questions about what is due and when, the tutor answers strictly from your actual tracked tasks. It does not reason its way to a date, and it does not fill a gap with something plausible. If the information is not in what you have given it, it says so plainly and offers general help instead of inventing a specific.

It cites what it used in ordinary language rather than footnotes — "your syllabus lists…", "from your Week 3 notes…" — which is enough to tell you whether an answer came from your material or from general knowledge. That distinction is the whole point.

The deadlines block carries titles, types, due dates, due times, weights, and whether you have checked something off.

Alongside it, the tutor gets the grade figures shown on that course's screen: your current percentage and letter, each category's average and weight, and how much of the grade has not been graded yet. So it can talk through a question like "what do I need on the final for a B?" with your real numbers. It is told to use those figures exactly as shown rather than work them out again, so its answer does not contradict your course screen.

It only knows the scores you have entered in Semora. If a grade is missing there, the tutor does not have it either. For an exact answer to what you need on the rest of the course, the what-if calculators in grade tracking are built for that one job.

Notes attach to a course, so open the tutor from a course rather than on its own — if you have not, the app tells you to instead of accepting a file with no course to belong to. PDFs and photos both work.

The reading happens on Semora's server, not on your phone. The file is stored privately in your account, and the first time a question needs it the server reads the text out of it and keeps that text, so the next question does not wait for it again.

One limit worth stating: Semora cannot read a file over roughly 6 MB. When a file cannot be read, the tutor names it and asks you to try again or upload it as a PDF, rather than quietly answering without it. If a large scanned lecture set will not go through, a smaller PDF export is the first thing to try.

Conversations are scoped to a course, which is what makes the grounding coherent — a thread for organic chemistry is not carrying context from your literature seminar.

The last 12 messages of a conversation are replayed each turn, roughly six exchanges of working memory. That is enough to follow up on an explanation without the thread quietly dragging an hour of unrelated context into every request.

There is also a general thread for questions that are not about one course. It does not carry any one course's syllabus or notes, but it does see your unfinished deadlines across every course for the next three weeks, plus anything overdue, so "what should I work on tonight?" gets a real answer.

Fifty tutor messages per rolling 24 hours per account — rolling, not a reset at midnight — and 4,000 characters per message, enforced in the composer and checked again on the server.

The AI model puts more thought into a hard question than a quick one, and writes a longer answer when you ask for one. Semora does not pin the Tutor to one model: it uses current models from the major AI providers and switches between them as they improve, and the privacy policy names the companies that receive your data.

Replies use light formatting — bold key terms, bullets, numbered steps, and math written in symbols — but no tables. If what you want is a long formatted document, this is the wrong surface.

The tutor is part of Pro, at $4.99 a month or $29.99 a year, bought with a card on the web or inside the iOS app, and applied account-wide either way.

• 50 messages per rolling 24 hours, per account
• 4,000 characters per message
• 12 previous messages replayed per turn
• Light formatting in replies, no tables

It is for the questions that need your context to answer: what does my syllabus say the exam covers, what did my Week 3 notes call this, what is actually due before Friday, how does my grading scale treat an 88.

It is a poor fit if what you want is a general tutor for a subject you are studying outside a tracked course, because the grounding has nothing to work with. It is also a poor fit if you want long formatted output.

And the same rule applies here as everywhere else in the app: it is worth exactly as much of your semester as you have entered. A course with a scanned syllabus, real deadlines and a few uploaded notes gets useful answers. An empty course gets a general chatbot.